Div2k Dataset for Super Resolution
- kaggle.com
Updated Mar 11, 2024
Share
Facebook
Twitter
EmailClick to copy linkLink copiedCiteTaki Hasan (2024). Div2k Dataset for Super Resolution [Dataset]. https://www.kaggle.com/datasets/takihasan/div2k-dataset-for-super-resolution/dataCroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.Dataset updatedMar 11, 2024AuthorsTaki HasanLicenseMIT Licensehttps://opensource.org/licenses/MIT
License information was derived automaticallyDescriptionThe DIV2K dataset is one of the most popular datasets used for image super-resolution, which is collected for NTIRE2017 and NTIRE2018 Super-Resolution Challenges. The dataset is composed of 800 images for training, 100 images for validation, and 100 images for testing. Each image has a 2K resolution. The official page of this dataset is here. This dataset contains the original high resolution images, bicubic downscaled 2x and 4x images. It contains the train and validation dataset. All the credits and right belongs to the original owners, I have uploaded here to conveniently create notebook and so that other can create notebooks for super resolution.
DIV2K Realistic Wild
- kaggle.com
Updated Nov 24, 2020ShareFacebookTwitterEmailClick to copy linkLink copiedCiteManas Sambare (2020). DIV2K Realistic Wild [Dataset]. https://www.kaggle.com/datasets/msambare/div2k-realistic-wild/versions/1CroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.Dataset updatedNov 24, 2020AuthorsManas SambareDescriptionDataset
This dataset was created by Manas Sambare
Contents
DIV2K_Valid_Compressed
- kaggle.com
Updated Oct 1, 2022ShareFacebookTwitterEmailClick to copy linkLink copiedCiteJIN (2022). DIV2K_Valid_Compressed [Dataset]. https://www.kaggle.com/datasets/jinssaa/div2k-valid-compressedCroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.Dataset updatedOct 1, 2022AuthorsJINDescriptionDataset
This dataset was created by JIN
Contents
DIV2K_valid_HRSect
- kaggle.com
Updated Jun 27, 2023ShareFacebookTwitterEmailClick to copy linkLink copiedCiteBNULChang (2023). DIV2K_valid_HRSect [Dataset]. https://www.kaggle.com/datasets/bnulchang/div2k-valid-hrsect/versions/1CroissantCroissant is a format for machine-learning datasets. Learn more about this at mlcommons.org/croissant.Dataset updatedJun 27, 2023AuthorsBNULChangDescriptionDataset
This dataset was created by BNULChang
Contents
DIV2K_bicubic_2x
- kaggle.com
zipUpdated Jun 1, 2021ShareFacebookTwitterEmailClick to copy linkLink copiedCite颀周 (2021). DIV2K_bicubic_2x [Dataset]. https://www.kaggle.com/chenqizhou/div2k-bicubic-2xzip(925846552 bytes)Available download formatsDataset updatedJun 1, 2021Authors颀周DescriptionDataset
This dataset was created by 颀周
Contents
It contains the following files:
Not seeing a result you expected?
Learn how you can add new datasets to our index.
FacebookTwitterEmailMIT Licensehttps://opensource.org/licenses/MIT
License information was derived automatically
The DIV2K dataset is one of the most popular datasets used for image super-resolution, which is collected for NTIRE2017 and NTIRE2018 Super-Resolution Challenges. The dataset is composed of 800 images for training, 100 images for validation, and 100 images for testing. Each image has a 2K resolution. The official page of this dataset is here. This dataset contains the original high resolution images, bicubic downscaled 2x and 4x images. It contains the train and validation dataset. All the credits and right belongs to the original owners, I have uploaded here to conveniently create notebook and so that other can create notebooks for super resolution.